{"id":"https://openalex.org/W4392909545","doi":"https://doi.org/10.1109/icassp48485.2024.10448506","title":"Text-Driven Talking Face Synthesis by Reprogramming Audio-Driven Models","display_name":"Text-Driven Talking Face Synthesis by Reprogramming Audio-Driven Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909545","doi":"https://doi.org/10.1109/icassp48485.2024.10448506"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448506","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101725649","display_name":"Jeongsoo Choi","orcid":"https://orcid.org/0009-0005-6817-604X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongsoo Choi","raw_affiliation_strings":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343629","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0002-6514-0018"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376689","display_name":"Se Jin Park","orcid":"https://orcid.org/0000-0002-1618-5906"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se Jin Park","raw_affiliation_strings":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["KAIST,School of Electrical Engineering,South Korea","School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"8065","last_page":"8069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9065999984741211,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6973245739936829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6523127555847168},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5253281593322754},{"id":"https://openalex.org/keywords/reprogramming","display_name":"Reprogramming","score":0.5203023552894592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43956243991851807},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3242048919200897},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1291804313659668}],"concepts":[{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6973245739936829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6523127555847168},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5253281593322754},{"id":"https://openalex.org/C77255625","wikidata":"https://www.wikidata.org/wiki/Q402093","display_name":"Reprogramming","level":3,"score":0.5203023552894592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43956243991851807},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3242048919200897},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1291804313659668},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C1491633281","wikidata":"https://www.wikidata.org/wiki/Q7868","display_name":"Cell","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448506","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2177770941","display_name":null,"funder_award_id":"4120200113769","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G30685149","display_name":null,"funder_award_id":"BK21 FOUR","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G5178579001","display_name":null,"funder_award_id":"NRF-2022R1A2C2005529","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5562307789","display_name":null,"funder_award_id":"BK21 FOUR","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6962113442","display_name":null,"funder_award_id":"4120200113769","funder_id":"https://openalex.org/F4320324161","funder_display_name":"Korea Advanced Institute of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2115252128","https://openalex.org/W2604379605","https://openalex.org/W2747874407","https://openalex.org/W2808631503","https://openalex.org/W2842511635","https://openalex.org/W2890952074","https://openalex.org/W2944294033","https://openalex.org/W2963290645","https://openalex.org/W2969985801","https://openalex.org/W2971634123","https://openalex.org/W3019952993","https://openalex.org/W3024147341","https://openalex.org/W3035574324","https://openalex.org/W3081492798","https://openalex.org/W3086926995","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3103801904","https://openalex.org/W3109114891","https://openalex.org/W3180770160","https://openalex.org/W3182714435","https://openalex.org/W3186090335","https://openalex.org/W3194357576","https://openalex.org/W3205904637","https://openalex.org/W3211147706","https://openalex.org/W4212774754","https://openalex.org/W4283795822","https://openalex.org/W4283818626","https://openalex.org/W4297808394","https://openalex.org/W4312444931","https://openalex.org/W4312578889","https://openalex.org/W4312975157","https://openalex.org/W4372263908","https://openalex.org/W4375868848","https://openalex.org/W4386066305","https://openalex.org/W4386075487","https://openalex.org/W4386075625","https://openalex.org/W6677618333","https://openalex.org/W6739901393","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W1631979401","https://openalex.org/W2395945797","https://openalex.org/W2129470469","https://openalex.org/W2368295610","https://openalex.org/W1543102035","https://openalex.org/W1497716427","https://openalex.org/W2946692299","https://openalex.org/W3014941007","https://openalex.org/W2183075003","https://openalex.org/W127416991"],"abstract_inverted_index":{"In":[0],"this":[1,50],"paper,":[2],"we":[3,22,52,82,184],"present":[4],"a":[5,18,84,91,123,134],"method":[6],"for":[7,40],"reprogramming":[8],"pre-trained":[9,67],"audio-driven":[10,47,68,177],"talking":[11,178,187],"face":[12,26,73,137,179,188],"synthesis":[13,74,180],"models":[14,181],"to":[15,54,107,121,146,175],"operate":[16],"in":[17,45,112,158],"text-driven":[19],"manner.":[20],"Consequently,":[21],"can":[23,172,185],"easily":[24],"generate":[25,186],"videos":[27,189],"that":[28,169],"articulate":[29],"the":[30,35,46,56,60,66,72,77,96,109,147,154,159,165],"provided":[31],"textual":[32],"sentences,":[33],"eliminating":[34],"necessity":[36],"of":[37,65,76,143,164],"recording":[38],"speech":[39],"each":[41],"inference,":[42],"as":[43],"required":[44],"model.":[48,80],"To":[49],"end,":[51],"propose":[53],"embed":[55],"input":[57,94,144],"text":[58,93,116,145,192],"into":[59,95],"learned":[61,148],"audio":[62,97,113,149,195],"latent":[63,98,150],"space":[64,99,151],"model,":[69],"while":[70,114],"preserving":[71],"capability":[75],"original":[78],"pretrained":[79],"Specifically,":[81],"devise":[83],"Text-to-Audio":[85],"Embedding":[86],"Module":[87],"(TAEM)":[88],"which":[89],"maps":[90],"given":[92],"by":[100,152],"modeling":[101],"pronunciation":[102],"and":[103,139,182],"duration":[104],"characteristics.":[105],"Furthermore,":[106],"consider":[108],"speaker":[110,125,129,155],"characteristics":[111,156],"using":[115],"inputs,":[117],"TAEM":[118],"is":[119,131],"designed":[120],"accept":[122],"visual":[124,128],"embedding.":[126],"The":[127,161],"embedding":[130],"derived":[132],"from":[133],"single":[135],"target":[136],"image":[138],"enables":[140],"improved":[141],"mapping":[142],"incorporating":[153],"inherent":[157],"audio.":[160],"main":[162],"advantages":[163],"proposed":[166],"framework":[167],"are":[168],"1)":[170],"it":[171],"be":[173],"applied":[174],"diverse":[176],"2)":[183],"with":[190,197],"either":[191],"inputs":[193,196],"or":[194],"high":[198],"flexibility.":[199]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}